Depth Q network distribution trolley-based automatic driving control method

A control method and automatic driving technology, applied in non-electric variable control, two-dimensional position/channel control, vehicle position/route/altitude control, etc., can solve the problem of high cost, speed up the training process, and avoid the loss of delivery vehicles Effect

Active Publication Date: 2018-09-28
SUZHOU UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current unmanned control vehicles mainly use radar sensors to measure the distance between the vehicle and obstacl

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Depth Q network distribution trolley-based automatic driving control method
  • Depth Q network distribution trolley-based automatic driving control method
  • Depth Q network distribution trolley-based automatic driving control method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0030] Example: see attached Figure 1~3 As shown, an automatic driving control method based on a deep Q network distribution trolley includes a sensor system, a control system, a drive system, and a power system. The sensor system collects environmental information and power system information, and combines environmental information and power The system information is transmitted to the control system, which is processed by the self-learning control method according to the received information, and then the sensor system receives the control information and controls the movement state of the delivery trolley.

[0031] In this embodiment, the overall control framework is the DeepQ-Network (DQN) in deep reinforcement learning, and the Q-learning (Q-Learning) algorithm in the field of reinforcement learning is used for control. Assuming that at each time step t = 1, 2, ..., the state of the Markov decision process observed by the unmanned car sensor system is s t , The control syst...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a depth Q network distribution trolley-based automatic driving control method. The method is characterized by comprising a sensing system, a control system, a driving system and an electric power system. The sensing system acquires the environment information and the information of the electric power system, and transmits the environment information and the information of the electric power system to the control system. The control system processes the received information through a self-learning control method to control the motion state of the distribution trolley. According to the method, a depth-strengthened learning optimization method with a safe distance is adopted in the control system of an unmanned control trolley. Meanwhile, the environment information acquired from the sensing system is processed. After that, a proper action is selected, and a control signal of the control system is transmitted to the driving system through the sensing system. As a result, the unmanned control trolley can execute the corresponding action to adapt to the variable road environment.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and control technology, and in particular relates to an automatic driving control method of a distribution car based on a deep Q network, which can perform self-learning and complete the control of an unmanned control car. Background technique [0002] In recent years, with the changes in the way of social life, various logistics companies undertake the distribution of more and more items. The main workflow of traditional logistics companies is: after the logistics arrives at the destination city, the courier delivery staff will manually deliver to the final destination. However, as the volume of logistics business increases, the delivery time requirements become shorter and shorter, and the tasks undertaken by express delivery personnel become heavier and heavier. Increasing the number of express delivery personnel will increase the labor cost of logistics companies. In addition, the manua...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G05D1/02G06K9/00
CPCG05D1/0221G06V20/58
Inventor 朱斐吴文伏玉琛周小科
Owner SUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap